This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "Agente de NF-3",
"nodes": [
{
"parameters": {
"public": true,
"initialMessages": "Ol\u00e1, sou ProcessIA.\nEnviei seu arqzip par atualizar meus dados, caso n\u00e3o queira pode fazer as perguntas que tenho alguns dados aqui.",
"options": {
"allowFileUploads": true
}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-2580,
-780
],
"id": "d2e72790-d762-499a-a90f-8bf0c1e8249c",
"name": "When chat message received"
},
{
"parameters": {
"binaryPropertyName": "=data0",
"outputPrefix": "=file_"
},
"type": "n8n-nodes-base.compression",
"typeVersion": 1.1,
"position": [
-1570,
-840
],
"id": "3a35c9ea-f3a2-4a7c-ad8a-efbb1422f2fd",
"name": "Compression"
},
{
"parameters": {
"binaryPropertyName": "file_0",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-1240,
-940
],
"id": "4d6951d3-a76b-41db-a435-4992558dfb22",
"name": "Extract from File"
},
{
"parameters": {
"options": {
"systemMessage": "Atue como ProcessIA, um agente de intelig\u00eancia financeira especializado em an\u00e1lise de notas fiscais e relat\u00f3rios tribut\u00e1rios, com 15 anos de experi\u00eancia atendendo empresas de m\u00e9dio e grande porte.\n\nSeu objetivo \u00e9 atender com precis\u00e3o e cordialidade as solicita\u00e7\u00f5es dos usu\u00e1rios via chat, utilizando exclusivamente a ferramenta Banco_dados, que busca informa\u00e7\u00f5es de notas fiscais (NF) em uma planilha do Google Sheets.\nNunca alucine informa\u00e7\u00f5es ou forne\u00e7a respostas gen\u00e9ricas sem consultar a ferramenta. Sempre consulte a ferramenta antes de qualquer resposta relacionada a dados fiscais.\n\n\ud83c\udfaf Diretrizes de Resposta:\nSempre se apresente para novos usu\u00e1rios, de forma breve, cordial e profissional.\nExemplo:\n\"Ol\u00e1! Sou o ProcessIA, seu assistente financeiro especializado em an\u00e1lise de notas fiscais. Em que posso ajudar voc\u00ea hoje?\"\n\nObrigatoriamente consulte a ferramenta Banco_dados antes de formular qualquer resposta.\n\u279d Se a ferramenta apresentar erro ou n\u00e3o retornar dados, informe isso de forma educada ao usu\u00e1rio, sem inventar informa\u00e7\u00f5es.\n\nNunca informe ao usu\u00e1rio que n\u00e3o tem acesso ao banco de dados enquanto a ferramenta estiver dispon\u00edvel.\n\nResponda de forma objetiva, em portugu\u00eas, utilizando os dados encontrados na consulta.\n\nApresente listas de forma organizada em bullet points, com nome da empresa e valor na frente.\n\nSeja positivo e mantenha uma linguagem profissional, sem uso excessivo de jarg\u00f5es t\u00e9cnicos.\n\n\ud83d\udcca Ferramenta Dispon\u00edvel:\nBanco_dados: Fun\u00e7\u00e3o que realiza busca de informa\u00e7\u00f5es de notas fiscais (NF) para responder perguntas e consultas do usu\u00e1rio.\nCalculadora: Para auxiliar nas solicita\u00e7\u00f5es de calculos (somas, multiplica\u00e7\u00f5es, divis\u00f5es, subtra\u00e7\u00f5es e percentuais, por exemplo)\n\n\ud83d\udcda Exemplos de Resposta:\nPergunta:\nQual \u00e9 o maior valor de compra ou nota que temos?\n\nResposta:\n\u2705 O maior valor de compra registrado \u00e9 de R$ 58.720,00 da empresa Comercial Santana Ltda.\n\nPergunta:\nListe as 10 maiores NF.\n\nResposta:\n\u2705 Aqui est\u00e1 a lista das 10 maiores notas fiscais:\n* Comercial Santana Ltda: R$ 58.720,00\n* Ind\u00fastria XPTO SA: R$ 53.200,00\n* Log\u00edstica Alfa Ltda: R$ 50.500,00\n(e assim por diante...)\n",
"returnIntermediateSteps": false
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
-1868,
-540
],
"id": "b1b8e161-b274-4207-9653-a6fefb1bc36b",
"name": "AI Agent",
"onError": "continueRegularOutput"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Switch').item.json.chatInput }}",
"contextWindowLength": 10
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
-1780,
-320
],
"id": "42f5742e-f6a0-43f7-8877-79bc823cf8b4",
"name": "Simple Memory"
},
{
"parameters": {
"binaryPropertyName": "file_1",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
-1240,
-740
],
"id": "2d4be509-c02e-4bfb-8824-83e96e6fa2af",
"name": "Extract from File1"
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash-lite",
"options": {
"maxOutputTokens": 2048,
"temperature": 0.4,
"topK": 32,
"topP": 1
}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
-1900,
-320
],
"id": "0ee346e4-2aed-4582-95e0-654038483d55",
"name": "Google Gemini Chat Model",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "combine",
"fieldsToMatchString": "['CHAVE DE ACESSO']",
"options": {}
},
"type": "n8n-nodes-base.merge",
"typeVersion": 3.1,
"position": [
-1020,
-840
],
"id": "0d6eb47e-4c6f-4ca9-a29b-ef6d5fcbc219",
"name": "Merge"
},
{
"parameters": {
"operation": "appendOrUpdate",
"documentId": {
"__rl": true,
"value": "1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw",
"mode": "list",
"cachedResultName": "i2a2",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw/edit?usp=drivesdk"
},
"sheetName": {
"__rl": true,
"value": "gid=0",
"mode": "list",
"cachedResultName": "P\u00e1gina1",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw/edit#gid=0"
},
"columns": {
"mappingMode": "autoMapInputData",
"value": {},
"matchingColumns": [
"CHAVE DE ACESSO"
],
"schema": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
-800,
-840
],
"id": "72c0dcbb-d51f-406a-a196-200d769521ad",
"name": "Google Sheets",
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "38fe7579-41ce-4b99-b33c-c82e71f5c315",
"leftValue": "={{ $json.files[0] }}",
"rightValue": "",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Anexo"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.chatInput }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"id": "0befcd8f-5048-4c19-ae12-ef31697283bf"
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "Texto"
}
]
},
"options": {
"allMatchingOutputs": true
}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.2,
"position": [
-2360,
-780
],
"id": "e74654fe-625b-4246-b662-77fe65ce4526",
"name": "Switch"
},
{
"parameters": {
"documentId": {
"__rl": true,
"value": "1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw",
"mode": "list",
"cachedResultName": "i2a2",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw/edit?usp=drivesdk"
},
"sheetName": {
"__rl": true,
"value": "gid=0",
"mode": "list",
"cachedResultName": "P\u00e1gina1",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1YWW9ExUC992aKEzHcu4tAGY4cKA_THNzsx9b5n_5Smw/edit#gid=0"
},
"options": {
"dataLocationOnSheet": {
"values": {
"rangeDefinition": "detectAutomatically",
"readRowsUntil": "firstEmptyRow"
}
},
"outputFormatting": {
"values": {
"general": "FORMATTED_VALUE",
"date": "FORMATTED_STRING"
}
}
}
},
"type": "n8n-nodes-base.googleSheetsTool",
"typeVersion": 4.5,
"position": [
-1660,
-320
],
"id": "03e66227-83ba-427f-a69d-fd9f4a47577e",
"name": "Banco_Dados",
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.toolCalculator",
"typeVersion": 1,
"position": [
-1520,
-320
],
"id": "30450c62-6e76-4ecb-8e0c-0d02ce83bdfe",
"name": "Calculator"
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"Compression": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
},
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Extract from File1": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Google Sheets",
"type": "main",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "Compression",
"type": "main",
"index": 0
}
],
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Banco_Dados": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Google Sheets": {
"main": [
[]
]
},
"Calculator": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "5f6456d8-ef7e-45dc-97a6-fdf6dc569240",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "Uh8TyFjjA7MHmodt",
"tags": [
{
"createdAt": "2025-06-21T15:06:18.854Z",
"updatedAt": "2025-06-21T15:06:18.854Z",
"id": "QtBnpscUmzI7i8ao",
"name": "i2a2"
}
]
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googlePalmApigoogleSheetsOAuth2Api
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Agente de NF-3. Uses chatTrigger, compression, agent, memoryBufferWindow. Chat trigger; 12 nodes.
Source: https://github.com/Kiemberly-ProcessIA/Grupo-de-estudos-/blob/29de04f38e371bcdb2fc2eaff589f93221cde026/json/agent.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
teste. Uses chatTrigger, agent, lmChatGroq, memoryBufferWindow. Chat trigger; 24 nodes.
Chat Trigger, Agent, Groq Chat +7
pix-zap. Uses chatTrigger, agent, toolCalculator, toolWikipedia. Chat trigger; 21 nodes.
Chat Trigger, Agent, Tool Calculator +7
Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to index a website and then interact with its content as if it were
Agent, OpenAI Chat, Memory Buffer Window +10
This workflow implements a WhatsApp-based virtual restaurant assistant that automates customer interaction from the first message to post-dining follow-up.
WhatsApp Trigger, WhatsApp, Guardrails +8
A fully automated Telegram-based personal finance tracker that: Accepts receipts as images, PDFs, or plain text Uses Google Gemini Vision for OCR & intelligent extraction Logs every expense into Googl
Telegram Trigger, Agent, Google Gemini Chat +8